Research Design: Nature, Elements and its types

Nature: A Research Design, in simple words, is a plan of action, a plan for collecting and
analyzing data in an economic, efficient and relevant manner. The purpose of preparing a
research design could be either to test a hypothesis or to give cause-effect relationship to the
given situation or to solve a problem scientifically. The working out of plan consist in reality of
making certain decisions with respect to

 What the study is about and types of data that are needed.
 Why these studies are been made.
 Where they needed data can be formed.
 Where or in what area, the study will be carried out.
 When and what periods of time, the study will include.
 How much material and how many cases will be made
 What basis of selection will be used.
 What techniques of gathering of data will be obtained.

Thus, the considerations which enter into making the decision regarding that,
what,where, when,how much, by what means, constitutes a plan of study on a study
design.

Some Definitions

 “Research Design is a master plan specifying the methods and procedures for collecting
data and analyzing the needed information.” - William Zikmund
 “Research Design is that plan, structure, and strategy of investigation conceived so as to
obtain answers to research questions and control variance.” – Kerlinger
 “A Research Design is the legitimate and systematic planning and directing of a piece of
research.” – P.V.Young
 “Research Design is the specification of the problem, conceptual definitions, derivation
of hypotheses to test, and defining of population to be studied”. - Martin Bulmer

Thus, the considerations which enter into making the decisions regarding that, what,
where, when, how much, by what means, constitutes a plan of study on a study design.

We can state the important features of a research design as under:

 It is a plan that specifies the sources and types of information relevant to research
problem.
 It is a strategy specifying which approach will be used for gathering and analyzing data.
 It also includes the time and cost budgets since most studies are done under these two
constraints.

One may split the overall research design into following parts:
 The Sampling Design: This deals with the method of selecting items to be observed for
the given study.
 The Observational Design: This relates to the conditions under which the observations
are to be made.
 The Statistical Design: This concern with the question of how many times are to be
observed and how the information and data gathered are to be analyzed.
 The Operational Design: This deals with the techniques by which the procedures
specified into sampling, statistical and observational design can be carried out.

Hence, through a research design you:

 Conceptualize an operational plan to undertake the various procedures and tasks required
to complete your study;
 Ensure that these procedures are adequate to obtain valid, objective and accurate answers
to the research questions. Kerlinger calls this function the ‘control of variance’. (1986)

Basic elements of research design

 Stating Problem i.e. to show whether it will be descriptive, explanatory or exploratory,

action, or theoretical research and what will it contribute to academics or to
understanding society.
 Review of other studies, i.e. going through the findings, hypothesis or theories
developed by other scholars in one’s own discipline or other disciplines.
 Operationalizing Concepts, i.e. giving specific meanings to terms used, e.g. ‘political
elite’, ‘development’, ‘sub-culture’, etc.
 Identifying Variables of Study, i.e. pointing out key variables in study and methods of
measurement.
 Fixing Sample, i.e. deciding the number of subjects from whom the data is to be
collected and how these subjects to be chosen are.
 Specifying tools of study, i.e. whether data are to be obtained through questionnaire,
schedule, interview, or observation.
 Designing the kind of analysis, i.e. whether any statistical test will be conducted and
which one? Specifying the logic of type of analysis chosen. Will it be cohort study?
 Fixing time schedule, i.e. providing various stages of the research process and
describing time to be devoted to each stage.
 Budget, i.e. if someone has sponsored the study. Amount is to be specified for salaries,
travelling, contingency, computer analysis and miscellaneous expenses.
Types of Research Design

1. Exploratory Research Design: Exploratory research studies are also termed as

formulative research studies. The main purpose of such studies is that of formulating
a problem for more precise investigation or of developing the working hypotheses
from an operational point of view. Such a study can have other functions as well
namely more structured investigation, phenomena which an investigator wishes to
study in the subsequent, etc. Such a study helps in clarifying concepts, establishing
priorities for further research, etc. The major emphasis in such studies is on the
discovery of ideas and insights. According to Hansraj, “Exploratory research is
necessary for establishing hypothesis and to get experience related with it for any
particular study.” Since most of the theories in Social Sciences are either too general
or too specific, therefore, these do not provide clear guidance for empirical research.
Exploratory research is therefore essential for gaining experience in formulation of
hypothesis for any definite investigation. This type of study is also essential for the
areas where not much is known.
However, there are certain conditions which are necessary for its success:
 Review of Pertinent literature: In this type of study, hypothesis is yet to be
developed and as such it is most desirable that researcher should gain out of
the experience of others. If he properly surveys the literature then he will be
saved from the trouble of ‘trial and error’. Many of his efforts, much of his
time, money and energy will be saved and it also helps him in knowing the
utility of hypothesis.
 Experience Survey: In exploratory studies, it is also essential that those
persons should be surveyed who have already done some work in field under
study. These people have the knowledge to guide and practical difficulties to
explain. These might be persons who might be social workers, senior
officials and professionals having a lot of untapped material at their disposal
on one hand and opportunity of viewing the problem from different angles
on the other.
 Selection of proper respondents: An exploratory study by all means is of
an exploratory nature and aims at providing insights and as such it is
essential that only such respondents should be selected who can provide real
insight to study, otherwise whole purpose of study will be defeated
 Proper questioning: The questions which are going .to be asked from the
subjects must be framed in advance and investigator is clear about the
concepts. He may take the help of books, professionals, etc.
 Analysis of insight stimulating cases: There are certain areas where there is
very little experience available to guide. In such areas analysis of insight
stimulating cases has been found very useful for intensive study.
 According to Zikmund, there are three purposes of formulating exploratory
research design:
 Diagnosing a situation
 Screening alternatives
 Discovering new ideas

2. Descriptive and Diagnostic Research Design: Descriptive research studies are

those studies which are concerned with describing the characteristics of a particular
individual, or of a group, whereas diagnostic research studies determine the frequency
with which something occurs or of its association with something else. The studies
concerning whether certain variables are associated are examples of diagnostic
research studies. As against this, studies concerned with specific predictions, with
narration of facts and characteristics concerning individual, group or situation are all
examples of descriptive research studies. Most of the social research comes under this
category. From the point of view of the research design, the descriptive as well as
diagnostic studies share common requirements and as such we may group together
these two types of research studies. The steps involved in both the types of research
studies are as under:
 Formulating the objective of the study
 Determining the methods of data collection
 Selecting the sample
 Collecting the data
 Processing and analyzing the data
 Reporting the findings

Basic features of Descriptive Research Design

 A Descriptive research design begins with the research about past form of the problem. It
does not bother about diagnostic action, approach, or activities.
 In a descriptive study, designs are not entirely motivated by hypothesis. Hypotheses are
formulated on the basis of the description of the existing data or material.
 In a descriptive study, primary aim is not to pose a problem and provide its solution, but
to acquire knowledge.
 Here the basic design is rigid. There is pre-planned design for analysis and advance
decisions are taken about operationalizing the study.
 The various steps of descriptive research are just like the steps of scientific method. For
e.g. selection of suitable subject, proper techniques of data collection, biased free
conclusion, analysis of data, etc.
 Research Design Type of Study
Exploratory or Formulative Descriptive/Diagnostic

Overall Design Flexible design (design must Rigid design (design must take
provide opportunity for enough provision for
considering different aspects protection against bias and
of the problem) must maximize reliability

1. Sampling Design Non-probability sampling Probability sampling design

design (purposive or (Random sampling)
judgment sampling)

2. Statistical design No pre-planned design for Pre-planned design for

analysis analysis

3. Observational Unstructured instruments for Structured or well thought out

design collection of data instruments for collection of
data
4. Operational design No fixed decisions about the
operational procedures Advanced decisions about
operational procedures

3. Research Design in case of hypothesis testing research studies

Hypothesis testing research studies (generally known as experimental studies) are

those where the researcher tests the hypotheses of causal relationships between
variables. Such studies require procedures that will not only reduce bias and increase
reliability, but will permit drawing inferences about causality. Usually experiments
meet this requirement. Hence, when we talk of research design in such studies, we
often mean the design of experiments. Professor R.A.Fisher’s name is associated with
experimental designs. Testing of hypotheses can be done through chi-square, F-test,
Z- test, etc. taking null and alternative hypothesis into account. In null hypothesis, we
presume that there is no significant difference between the observed variables or they
are equal, whereas in alternative hypothesis we assume that there is significant
difference in the observed variables. Alternative hypothesis is usually the one which
one wishes to prove and the null hypothesis is the one which one wishes to disprove.